© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7025
    Prev
    Next
    INDEX
    Explanations

    instances where something is still ongoing or in existence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing existence or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.63
    guyen
    -0.63
    ision
    -0.63
    sonian
    -0.62
    ggles
    -0.62
    imeter
    -0.61
    PsyNetMessage
    -0.60
    osterone
    -0.60
    isson
    -0.60
    ingly
    -0.59
    POSITIVE LOGITS
     alive
    1.52
     here
    1.14
     around
    1.11
     Alive
    1.09
     there
    1.09
     active
    1.09
     awake
    1.07
     present
    1.07
     asleep
    0.98
     lurking
    0.98
    Activations Density 0.334%

    No Known Activations